The Large Language Model revolution started with the advent of transformers in 2017. Since then there has been an exponential growth in the models trained. Models with 100B+ parameters have been trained. These pre-trained models have changed the way NLP is done. It is much easier to pick a pre-trained model and fine-tune it for a downstream task ( sentiment, question answering, entity recognition etc.. ) than training a model from scratch.
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
Link
CopyMonkey generates and optimizes Amazon listings in seconds. AI helps place all of the important keywords in your Amazon listing to get you ranking organically on the first page.
Link
This year, we see significant progress in the field of generative models. Stable Diffusion 🎨 creates hyperrealistic art. ChatGPT 💬 answers questions to the meaning of life. Galactica 🧬 learns humanity’s scientific knowledge but also reveals the limitations of large language models.
Link
Use Lightning, the hyper-minimalistic framework, to build machine learning components that can plug into existing ML workflows. A Lightning component organizes arbitrary code to run on the cloud, manage its own infrastructure, cloud costs, networking, and more. Focus on component logic and not engineering.
Link
2022 comes to an end and it is about time to sit down and reflect upon the achievements made in Graph ML as well as to hypothesize about possible breakthroughs in 2023.
Link
We first study what graphs are, why they are used, and how best to represent them. We then cover briefly how people learn on graphs, from pre-neural methods (exploring graph features at the same time) to what are commonly called Graph Neural Networks. Lastly, we peek into the world of Transformers for graphs.
Link
We believe that by doing this we will create a revolution in innovation in language. In the same way that stable-diffusion helped the world make art and images in new ways we hope Open Assistant can help improve the world by improving language itself.
Link
Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms. The CLRS Algorithmic Reasoning Benchmark (CLRS) consolidates and extends previous work toward evaluation algorithmic reasoning by providing a suite of implementations of classical algorithms. These algorithms have been selected from the third edition of the standard Introduction to Algorithms by Cormen, Leiserson, Rivest and Stein.
Link
Torchview provides visualization of pytorch models in the form of visual graphs. Visualization includes tensors, modules, torch.functions and info such as input/output shapes.
Link
This is the official repository of DeepMTP, a deep learning framework that can be used with multi-target prediction (MTP) problems. MTP can be seen as an umbrella term that cover many subareas of machine learning, which include multi-label classification (MLC), multivariate regression (MTR), multi-task learning (MTL), dyadic prediction (DP), and matrix completion (MC). The implementation is mainly written in Python and uses Pytorch for the implementation of the neural network. The goal is for any user to be able to train a model using only a few lines of code.
AlphaTensor is a novel AI solution to discover mathematical algorithms with Reinforcement Learning. Learn everything you need to know about AlphaTensor in this comprehensive introduction.
Link
